explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-09-21 03:19:13 +03:00
Code Issues Packages Projects Releases Wiki Activity

Tidy up and fix formatting and imports

Browse Source
This commit is contained in:
ines 2017-04-15 13:05:15 +02:00
parent fefe6684cd
commit 0739ae7b76
15 changed files with 251 additions and 230 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
spacy/compat.py
View File

@ -3,7 +3,7 @@ from __future__ import unicode_literals
import six
import sys
import json
import ujson
try:
import cPickle as pickle
@ -28,14 +28,14 @@ if is_python2:
unicode_ = unicode
basestring_ = basestring
input_ = raw_input
json_dumps = lambda data: json.dumps(data, indent=2).decode('utf8')
json_dumps = lambda data: ujson.dumps(data, indent=2).decode('utf8')
elif is_python3:
bytes_ = bytes
unicode_ = str
basestring_ = str
input_ = input
json_dumps = lambda data: json.dumps(data, indent=2)
json_dumps = lambda data: ujson.dumps(data, indent=2)
def symlink_to(orig, dest):

3
spacy/deprecated.py
View File

@ -1,3 +1,6 @@
# coding: utf8
from __future__ import unicode_literals
from pathlib import Path
from . import about

8
spacy/syntax/_parse_features.pyx
View File

@ -7,17 +7,17 @@ out of "context") is in features/extractor.pyx
The atomic feature names are listed in a big enum, so that the feature tuples
can refer to them.
"""
from libc.string cimport memset
# coding: utf-8
from __future__ import unicode_literals
from libc.string cimport memset
from itertools import combinations
from cymem.cymem cimport Pool
from ..structs cimport TokenC
from .stateclass cimport StateClass
from ._state cimport StateC
from cymem.cymem cimport Pool
cdef inline void fill_token(atom_t* context, const TokenC* token) nogil:
if token is NULL:

23
spacy/syntax/arc_eager.pyx
View File

@ -1,29 +1,26 @@
# cython: profile=True
# cython: cdivision=True
# cython: infer_types=True
# coding: utf-8
from __future__ import unicode_literals
from cpython.ref cimport PyObject, Py_INCREF, Py_XDECREF
import ctypes
import os
from ..structs cimport TokenC
from libc.stdint cimport uint32_t
from libc.string cimport memcpy
from cymem.cymem cimport Pool
from .stateclass cimport StateClass
from ._state cimport StateC, is_space_token
from .nonproj import PseudoProjectivity
from .nonproj import is_nonproj_tree
from .transition_system cimport do_func_t, get_cost_func_t
from .transition_system cimport move_cost_func_t, label_cost_func_t
from ..gold cimport GoldParse
from ..gold cimport GoldParseC
from ..attrs cimport TAG, HEAD, DEP, ENT_IOB, ENT_TYPE, IS_SPACE
from ..lexeme cimport Lexeme
from libc.stdint cimport uint32_t
from libc.string cimport memcpy
from cymem.cymem cimport Pool
from .stateclass cimport StateClass
from ._state cimport StateC, is_space_token
from .nonproj import PseudoProjectivity
from .nonproj import is_nonproj_tree
from ..structs cimport TokenC
DEF NON_MONOTONIC = True

31
spacy/syntax/beam_parser.pyx
View File

@ -1,50 +1,34 @@
"""
MALT-style dependency parser
"""
# cython: profile=True
# cython: experimental_cpp_class_def=True
# cython: cdivision=True
# cython: infer_types=True
"""
MALT-style dependency parser
"""
from __future__ import unicode_literals
# coding: utf-8
from __future__ import unicode_literals, print_function
cimport cython
from cpython.ref cimport PyObject, Py_INCREF, Py_XDECREF
from libc.stdint cimport uint32_t, uint64_t
from libc.string cimport memset, memcpy
from libc.stdlib cimport rand
from libc.math cimport log, exp, isnan, isinf
import random
import os.path
from os import path
import shutil
import json
import math
from cymem.cymem cimport Pool, Address
from murmurhash.mrmr cimport real_hash64 as hash64
from thinc.typedefs cimport weight_t, class_t, feat_t, atom_t, hash_t
from util import Config
from thinc.linear.features cimport ConjunctionExtracter
from thinc.structs cimport FeatureC, ExampleC
from thinc.extra.search cimport Beam
from thinc.extra.search cimport MaxViolation
from thinc.extra.search cimport Beam, MaxViolation
from thinc.extra.eg cimport Example
from thinc.extra.mb cimport Minibatch
from ..structs cimport TokenC
from ..tokens.doc cimport Doc
from ..strings cimport StringStore
from .transition_system cimport TransitionSystem, Transition
from ..gold cimport GoldParse
from . import _parse_features
from ._parse_features cimport CONTEXT_SIZE
from ._parse_features cimport fill_context
@ -266,4 +250,3 @@ def is_gold(StateClass state, GoldParse gold, StringStore strings):
id_, word, tag, head, dep, ner = gold.orig_annot[gold.cand_to_gold[i]]
truth.add((id_, head, dep))
return truth == predicted

11
spacy/syntax/iterators.pyx
View File

@ -1,9 +1,14 @@
from spacy.parts_of_speech cimport NOUN, PROPN, PRON
# coding: utf-8
from __future__ import unicode_literals
from ..parts_of_speech cimport NOUN, PROPN, PRON
def english_noun_chunks(obj):
'''Detect base noun phrases from a dependency parse.
Works on both Doc and Span.'''
"""
Detect base noun phrases from a dependency parse.
Works on both Doc and Span.
"""
labels = ['nsubj', 'dobj', 'nsubjpass', 'pcomp', 'pobj',
'attr', 'ROOT', 'root']
doc = obj.doc # Ensure works on both Doc and Span.

15
spacy/syntax/ner.pyx
View File

@ -1,17 +1,16 @@
# coding: utf-8
from __future__ import unicode_literals
from .transition_system cimport Transition
from .transition_system cimport do_func_t
from ..structs cimport TokenC, Entity
from thinc.typedefs cimport weight_t
from ..gold cimport GoldParseC
from ..gold cimport GoldParse
from ..attrs cimport ENT_TYPE, ENT_IOB
from .stateclass cimport StateClass
from ._state cimport StateC
from .transition_system cimport Transition
from .transition_system cimport do_func_t
from ..structs cimport TokenC, Entity
from ..gold cimport GoldParseC
from ..gold cimport GoldParse
from ..attrs cimport ENT_TYPE, ENT_IOB
cdef enum:

5
spacy/syntax/nonproj.pyx
View File

@ -1,8 +1,9 @@
# coding: utf-8
from __future__ import unicode_literals
from copy import copy
from ..tokens.doc cimport Doc
from spacy.attrs import DEP, HEAD
from ..attrs import DEP, HEAD
def ancestors(tokenid, heads):
@ -201,5 +202,3 @@ class PseudoProjectivity:
filtered_sents.append(((ids,words,tags,heads,filtered_labels,iob), ctnts))
filtered.append((raw_text, filtered_sents))
return filtered

80
spacy/syntax/parser.pyx
View File

@ -1,56 +1,44 @@
# cython: infer_types=True
"""
MALT-style dependency parser
"""
# coding: utf-8
# cython: infer_types=True
from __future__ import unicode_literals
from collections import Counter
import ujson
cimport cython
cimport cython.parallel
from cpython.ref cimport PyObject, Py_INCREF, Py_XDECREF
from cpython.exc cimport PyErr_CheckSignals
from libc.stdint cimport uint32_t, uint64_t
from libc.string cimport memset, memcpy
from libc.stdlib cimport malloc, calloc, free
import os.path
from collections import Counter
from os import path
import shutil
import json
import sys
from .nonproj import PseudoProjectivity
from cymem.cymem cimport Pool, Address
from murmurhash.mrmr cimport hash64
from thinc.typedefs cimport weight_t, class_t, feat_t, atom_t, hash_t
from thinc.linear.avgtron cimport AveragedPerceptron
from thinc.linalg cimport VecVec
from thinc.structs cimport SparseArrayC
from thinc.structs cimport SparseArrayC, FeatureC, ExampleC
from thinc.extra.eg cimport Example
from cymem.cymem cimport Pool, Address
from murmurhash.mrmr cimport hash64
from preshed.maps cimport MapStruct
from preshed.maps cimport map_get
from thinc.structs cimport FeatureC
from thinc.structs cimport ExampleC
from thinc.extra.eg cimport Example
from util import Config
from ..structs cimport TokenC
from ..tokens.doc cimport Doc
from ..strings cimport StringStore
from .transition_system import OracleError
from .transition_system cimport TransitionSystem, Transition
from ..gold cimport GoldParse
from . import _parse_features
from ._parse_features cimport CONTEXT_SIZE
from ._parse_features cimport fill_context
from .stateclass cimport StateClass
from ._state cimport StateC
from .nonproj import PseudoProjectivity
from .transition_system import OracleError
from .transition_system cimport TransitionSystem, Transition
from ..structs cimport TokenC
from ..tokens.doc cimport Doc
from ..strings cimport StringStore
from ..gold cimport GoldParse
USE_FTRL = False
DEBUG = False
@ -80,7 +68,9 @@ cdef class ParserModel(AveragedPerceptron):
return nr_feat
def update(self, Example eg, itn=0):
'''Does regression on negative cost. Sort of cute?'''
"""
Does regression on negative cost. Sort of cute?
"""
self.time += 1
cdef int best = arg_max_if_gold(eg.c.scores, eg.c.costs, eg.c.nr_class)
cdef int guess = eg.guess
@ -132,10 +122,13 @@ cdef class ParserModel(AveragedPerceptron):
cdef class Parser:
"""Base class of the DependencyParser and EntityRecognizer."""
"""
Base class of the DependencyParser and EntityRecognizer.
"""
@classmethod
def load(cls, path, Vocab vocab, TransitionSystem=None, require=False, **cfg):
"""Load the statistical model from the supplied path.
"""
Load the statistical model from the supplied path.
Arguments:
path (Path):
@ -148,7 +141,7 @@ cdef class Parser:
The newly constructed object.
"""
with (path / 'config.json').open() as file_:
cfg = json.load(file_)
cfg = ujson.load(file_)
# TODO: remove this shim when we don't have to support older data
if 'labels' in cfg and 'actions' not in cfg:
cfg['actions'] = cfg.pop('labels')
@ -168,7 +161,8 @@ cdef class Parser:
return self
def __init__(self, Vocab vocab, TransitionSystem=None, ParserModel model=None, **cfg):
"""Create a Parser.
"""
Create a Parser.
Arguments:
vocab (Vocab):
@ -198,7 +192,8 @@ cdef class Parser:
return (Parser, (self.vocab, self.moves, self.model), None, None)
def __call__(self, Doc tokens):
"""Apply the entity recognizer, setting the annotations onto the Doc object.
"""
Apply the entity recognizer, setting the annotations onto the Doc object.
Arguments:
doc (Doc): The document to be processed.
@ -215,7 +210,8 @@ cdef class Parser:
self.moves.finalize_doc(tokens)
def pipe(self, stream, int batch_size=1000, int n_threads=2):
"""Process a stream of documents.
"""
Process a stream of documents.
Arguments:
stream: The sequence of documents to process.
@ -303,7 +299,8 @@ cdef class Parser:
return 0
def update(self, Doc tokens, GoldParse gold, itn=0):
"""Update the statistical model.
"""
Update the statistical model.
Arguments:
doc (Doc):
@ -342,7 +339,8 @@ cdef class Parser:
return loss
def step_through(self, Doc doc, GoldParse gold=None):
"""Set up a stepwise state, to introspect and control the transition sequence.
"""
Set up a stepwise state, to introspect and control the transition sequence.
Arguments:
doc (Doc): The document to step through.
@ -426,7 +424,9 @@ cdef class StepwiseState:
@property
def costs(self):
'''Find the action-costs for the current state'''
"""
Find the action-costs for the current state.
"""
self.parser.moves.set_costs(self.eg.c.is_valid, self.eg.c.costs,
self.stcls, self.gold)
costs = {}

8
spacy/syntax/stateclass.pyx
View File

@ -1,5 +1,9 @@
# coding: utf-8
from __future__ import unicode_literals
from libc.string cimport memcpy, memset
from libc.stdint cimport uint32_t
from ..vocab cimport EMPTY_LEXEME
from ..structs cimport Entity
from ..lexeme cimport Lexeme
@ -28,6 +32,6 @@ cdef class StateClass:
top = words[self.S(0)] + '_%d' % self.S_(0).head
second = words[self.S(1)] + '_%d' % self.S_(1).head
third = words[self.S(2)] + '_%d' % self.S_(2).head
n0 = words[self.B(0)]
n1 = words[self.B(1)]
n0 = words[self.B(0)]
n1 = words[self.B(1)]
return ' '.join((third, second, top, '|', n0, n1))

5
spacy/syntax/transition_system.pyx
View File

@ -1,4 +1,8 @@
# cython: infer_types=True
# coding: utf-8
from __future__ import unicode_literals
from cpython.ref cimport PyObject, Py_INCREF, Py_XDECREF
from cymem.cymem cimport Pool
from thinc.typedefs cimport weight_t
from collections import defaultdict
@ -6,7 +10,6 @@ from collections import defaultdict
from ..structs cimport TokenC
from .stateclass cimport StateClass
from ..attrs cimport TAG, HEAD, DEP, ENT_TYPE, ENT_IOB
from cpython.ref cimport PyObject, Py_INCREF, Py_XDECREF
cdef weight_t MIN_SCORE = -90000

18
spacy/syntax/util.py
View File

@ -1,18 +0,0 @@
from os import path
import json
class Config(object):
def __init__(self, **kwargs):
for key, value in kwargs.items():
setattr(self, key, value)
def get(self, attr, default=None):
return self.__dict__.get(attr, default)
@classmethod
def write(cls, model_dir, name, **kwargs):
open(path.join(model_dir, '%s.json' % name), 'w').write(json.dumps(kwargs))
@classmethod
def read(cls, model_dir, name):
return cls(**json.load(open(path.join(model_dir, '%s.json' % name))))

93
spacy/tokens/doc.pyx
View File

@ -1,15 +1,18 @@
# coding: utf8
from __future__ import unicode_literals
cimport cython
cimport numpy as np
import numpy
import numpy.linalg
import struct
from libc.string cimport memcpy, memset
from libc.stdint cimport uint32_t
from libc.math cimport sqrt
import numpy
import numpy.linalg
import struct
cimport numpy as np
import six
import warnings
from .span cimport Span
from .token cimport Token
from ..lexeme cimport Lexeme
from ..lexeme cimport EMPTY_LEXEME
from ..typedefs cimport attr_t, flags_t
@ -19,11 +22,10 @@ from ..attrs cimport POS, LEMMA, TAG, DEP, HEAD, SPACY, ENT_IOB, ENT_TYPE
from ..parts_of_speech cimport CCONJ, PUNCT, NOUN
from ..parts_of_speech cimport univ_pos_t
from ..lexeme cimport Lexeme
from .span cimport Span
from .token cimport Token
from ..serialize.bits cimport BitArray
from ..util import normalize_slice
from ..syntax.iterators import CHUNKERS
from ..compat import is_config
DEF PADDING = 5
@ -76,7 +78,7 @@ cdef class Doc:
"""
def __init__(self, Vocab vocab, words=None, spaces=None, orths_and_spaces=None):
'''
"""
Create a Doc object.
Aside: Implementation
@ -97,7 +99,7 @@ cdef class Doc:
A list of boolean values, of the same length as words. True
means that the word is followed by a space, False means it is not.
If None, defaults to [True]*len(words)
'''
"""
self.vocab = vocab
size = 20
self.mem = Pool()
@ -158,7 +160,7 @@ cdef class Doc:
self.is_parsed = True
def __getitem__(self, object i):
'''
"""
doc[i]
Get the Token object at position i, where i is an integer.
Negative indexing is supported, and follows the usual Python
@ -172,7 +174,7 @@ cdef class Doc:
are not supported, as `Span` objects must be contiguous (cannot have gaps).
You can use negative indices and open-ended ranges, which have their
normal Python semantics.
'''
"""
if isinstance(i, slice):
start, stop = normalize_slice(len(self), i.start, i.stop, i.step)
return Span(self, start, stop, label=0)
@ -186,7 +188,7 @@ cdef class Doc:
return Token.cinit(self.vocab, &self.c[i], i, self)
def __iter__(self):
'''
"""
for token in doc
Iterate over `Token` objects, from which the annotations can
be easily accessed. This is the main way of accessing Token
@ -194,7 +196,7 @@ cdef class Doc:
Python. If faster-than-Python speeds are required, you can
instead access the annotations as a numpy array, or access the
underlying C data directly from Cython.
'''
"""
cdef int i
for i in range(self.length):
if self._py_tokens[i] is not None:
@ -203,10 +205,10 @@ cdef class Doc:
yield Token.cinit(self.vocab, &self.c[i], i, self)
def __len__(self):
'''
"""
len(doc)
The number of tokens in the document.
'''
"""
return self.length
def __unicode__(self):
@ -216,7 +218,7 @@ cdef class Doc:
return u''.join([t.text_with_ws for t in self]).encode('utf-8')
def __str__(self):
if six.PY3:
if is_config(python3=True):
return self.__unicode__()
return self.__bytes__()
@ -228,7 +230,8 @@ cdef class Doc:
return self
def similarity(self, other):
'''Make a semantic similarity estimate. The default estimate is cosine
"""
Make a semantic similarity estimate. The default estimate is cosine
similarity using an average of word vectors.
Arguments:
@ -237,7 +240,7 @@ cdef class Doc:
Return:
score (float): A scalar similarity score. Higher is more similar.
'''
"""
if 'similarity' in self.user_hooks:
return self.user_hooks['similarity'](self, other)
if self.vector_norm == 0 or other.vector_norm == 0:
@ -245,9 +248,9 @@ cdef class Doc:
return numpy.dot(self.vector, other.vector) / (self.vector_norm * other.vector_norm)
property has_vector:
'''
"""
A boolean value indicating whether a word vector is associated with the object.
'''
"""
def __get__(self):
if 'has_vector' in self.user_hooks:
return self.user_hooks['has_vector'](self)
@ -255,11 +258,11 @@ cdef class Doc:
return any(token.has_vector for token in self)
property vector:
'''
"""
A real-valued meaning representation. Defaults to an average of the token vectors.
Type: numpy.ndarray[ndim=1, dtype='float32']
'''
"""
def __get__(self):
if 'vector' in self.user_hooks:
return self.user_hooks['vector'](self)
@ -294,17 +297,21 @@ cdef class Doc:
return self.text
property text:
'''A unicode representation of the document text.'''
"""
A unicode representation of the document text.
"""
def __get__(self):
return u''.join(t.text_with_ws for t in self)
property text_with_ws:
'''An alias of Doc.text, provided for duck-type compatibility with Span and Token.'''
"""
An alias of Doc.text, provided for duck-type compatibility with Span and Token.
"""
def __get__(self):
return self.text
property ents:
'''
"""
Yields named-entity `Span` objects, if the entity recognizer
has been applied to the document. Iterate over the span to get
individual Token objects, or access the label:
@ -318,7 +325,7 @@ cdef class Doc:
assert ents[0].label_ == 'PERSON'
assert ents[0].orth_ == 'Best'
assert ents[0].text == 'Mr. Best'
'''
"""
def __get__(self):
cdef int i
cdef const TokenC* token
@ -382,13 +389,13 @@ cdef class Doc:
self.c[start].ent_iob = 3
property noun_chunks:
'''
"""
Yields base noun-phrase #[code Span] objects, if the document
has been syntactically parsed. A base noun phrase, or
'NP chunk', is a noun phrase that does not permit other NPs to
be nested within it – so no NP-level coordination, no prepositional
phrases, and no relative clauses. For example:
'''
phrases, and no relative clauses.
"""
def __get__(self):
if not self.is_parsed:
raise ValueError(
@ -496,7 +503,8 @@ cdef class Doc:
return output
def count_by(self, attr_id_t attr_id, exclude=None, PreshCounter counts=None):
"""Produce a dict of {attribute (int): count (ints)} frequencies, keyed
"""
Produce a dict of {attribute (int): count (ints)} frequencies, keyed
by the values of the given attribute ID.
Example:
@ -563,8 +571,9 @@ cdef class Doc:
self.c[i] = parsed[i]
def from_array(self, attrs, array):
'''Write to a `Doc` object, from an `(M, N)` array of attributes.
'''
"""
Write to a `Doc` object, from an `(M, N)` array of attributes.
"""
cdef int i, col
cdef attr_id_t attr_id
cdef TokenC* tokens = self.c
@ -603,19 +612,23 @@ cdef class Doc:
return self
def to_bytes(self):
'''Serialize, producing a byte string.'''
"""
Serialize, producing a byte string.
"""
byte_string = self.vocab.serializer.pack(self)
cdef uint32_t length = len(byte_string)
return struct.pack('I', length) + byte_string
def from_bytes(self, data):
'''Deserialize, loading from bytes.'''
"""
Deserialize, loading from bytes.
"""
self.vocab.serializer.unpack_into(data[4:], self)
return self
@staticmethod
def read_bytes(file_):
'''
"""
A static method, used to read serialized #[code Doc] objects from
a file. For example:
@ -630,7 +643,7 @@ cdef class Doc:
for byte_string in Doc.read_bytes(file_):
docs.append(Doc(nlp.vocab).from_bytes(byte_string))
assert len(docs) == 2
'''
"""
keep_reading = True
while keep_reading:
try:
@ -644,7 +657,8 @@ cdef class Doc:
yield n_bytes_str + data
def merge(self, int start_idx, int end_idx, *args, **attributes):
"""Retokenize the document, such that the span at doc.text[start_idx : end_idx]
"""
Retokenize the document, such that the span at doc.text[start_idx : end_idx]
is merged into a single token. If start_idx and end_idx do not mark start
and end token boundaries, the document remains unchanged.
@ -658,7 +672,6 @@ cdef class Doc:
token (Token):
The newly merged token, or None if the start and end indices did
not fall at token boundaries.
"""
cdef unicode tag, lemma, ent_type
if len(args) == 3:

72
spacy/tokens/span.pyx
View File

@ -1,26 +1,31 @@
# coding: utf8
from __future__ import unicode_literals
from collections import defaultdict
cimport numpy as np
import numpy
import numpy.linalg
cimport numpy as np
from libc.math cimport sqrt
import six
from .doc cimport token_by_start, token_by_end
from ..structs cimport TokenC, LexemeC
from ..typedefs cimport flags_t, attr_t, hash_t
from ..attrs cimport attr_id_t
from ..parts_of_speech cimport univ_pos_t
from ..util import normalize_slice
from .doc cimport token_by_start, token_by_end
from ..attrs cimport IS_PUNCT, IS_SPACE
from ..lexeme cimport Lexeme
from ..compat import is_config
cdef class Span:
"""A slice from a Doc object."""
"""
A slice from a Doc object.
"""
def __cinit__(self, Doc doc, int start, int end, int label=0, vector=None,
vector_norm=None):
'''Create a Span object from the slice doc[start : end]
"""
Create a Span object from the slice doc[start : end]
Arguments:
doc (Doc): The parent document.
@ -30,7 +35,7 @@ cdef class Span:
vector (ndarray[ndim=1, dtype='float32']): A meaning representation of the span.
Returns:
Span The newly constructed object.
'''
"""
if not (0 <= start <= end <= len(doc)):
raise IndexError
@ -68,7 +73,7 @@ cdef class Span:
return self.end - self.start
def __repr__(self):
if six.PY3:
if is_config(python3=True):
return self.text
return self.text.encode('utf-8')
@ -89,7 +94,8 @@ cdef class Span:
yield self.doc[i]
def merge(self, *args, **attributes):
"""Retokenize the document, such that the span is merged into a single token.
"""
Retokenize the document, such that the span is merged into a single token.
Arguments:
**attributes:
@ -102,7 +108,8 @@ cdef class Span:
return self.doc.merge(self.start_char, self.end_char, *args, **attributes)
def similarity(self, other):
'''Make a semantic similarity estimate. The default estimate is cosine
"""
Make a semantic similarity estimate. The default estimate is cosine
similarity using an average of word vectors.
Arguments:
@ -111,7 +118,7 @@ cdef class Span:
Return:
score (float): A scalar similarity score. Higher is more similar.
'''
"""
if 'similarity' in self.doc.user_span_hooks:
self.doc.user_span_hooks['similarity'](self, other)
if self.vector_norm == 0.0 or other.vector_norm == 0.0:
@ -133,11 +140,12 @@ cdef class Span:
self.end = end + 1
property sent:
'''The sentence span that this span is a part of.
"""
The sentence span that this span is a part of.
Returns:
Span The sentence this is part of.
'''
"""
def __get__(self):
if 'sent' in self.doc.user_span_hooks:
return self.doc.user_span_hooks['sent'](self)
@ -198,13 +206,13 @@ cdef class Span:
return u''.join([t.text_with_ws for t in self])
property noun_chunks:
'''
"""
Yields base noun-phrase #[code Span] objects, if the document
has been syntactically parsed. A base noun phrase, or
'NP chunk', is a noun phrase that does not permit other NPs to
be nested within it – so no NP-level coordination, no prepositional
phrases, and no relative clauses. For example:
'''
"""
def __get__(self):
if not self.doc.is_parsed:
raise ValueError(
@ -223,17 +231,16 @@ cdef class Span:
yield span
property root:
"""The token within the span that's highest in the parse tree. If there's a tie, the earlist is prefered.
"""
The token within the span that's highest in the parse tree. If there's a
tie, the earlist is prefered.
Returns:
Token: The root token.
i.e. has the
shortest path to the root of the sentence (or is the root itself).
If multiple words are equally high in the tree, the first word is taken.
For example:
i.e. has the shortest path to the root of the sentence (or is the root
itself). If multiple words are equally high in the tree, the first word
is taken. For example:
>>> toks = nlp(u'I like New York in Autumn.')
@ -303,7 +310,8 @@ cdef class Span:
return self.doc[root]
property lefts:
"""Tokens that are to the left of the span, whose head is within the Span.
"""
Tokens that are to the left of the span, whose head is within the Span.
Yields: Token A left-child of a token of the span.
"""
@ -314,7 +322,8 @@ cdef class Span:
yield left
property rights:
"""Tokens that are to the right of the Span, whose head is within the Span.
"""
Tokens that are to the right of the Span, whose head is within the Span.
Yields: Token A right-child of a token of the span.
"""
@ -325,7 +334,8 @@ cdef class Span:
yield right
property subtree:
"""Tokens that descend from tokens in the span, but fall outside it.
"""
Tokens that descend from tokens in the span, but fall outside it.
Yields: Token A descendant of a token within the span.
"""
@ -337,7 +347,9 @@ cdef class Span:
yield from word.subtree
property ent_id:
'''An (integer) entity ID. Usually assigned by patterns in the Matcher.'''
"""
An (integer) entity ID. Usually assigned by patterns in the Matcher.
"""
def __get__(self):
return self.root.ent_id
@ -345,9 +357,11 @@ cdef class Span:
# TODO
raise NotImplementedError(
"Can't yet set ent_id from Span. Vote for this feature on the issue "
"tracker: http://github.com/spacy-io/spaCy")
"tracker: http://github.com/explosion/spaCy/issues")
property ent_id_:
'''A (string) entity ID. Usually assigned by patterns in the Matcher.'''
"""
A (string) entity ID. Usually assigned by patterns in the Matcher.
"""
def __get__(self):
return self.root.ent_id_
@ -355,7 +369,7 @@ cdef class Span:
# TODO
raise NotImplementedError(
"Can't yet set ent_id_ from Span. Vote for this feature on the issue "
"tracker: http://github.com/spacy-io/spaCy")
"tracker: http://github.com/explosion/spaCy/issues")
property orth_:
def __get__(self):
@ -397,5 +411,5 @@ cdef int _count_words_to_root(const TokenC* token, int sent_length) except -1:
raise RuntimeError(
"Array bounds exceeded while searching for root word. This likely "
"means the parse tree is in an invalid state. Please report this "
"issue here: http://github.com/honnibal/spaCy/")
"issue here: http://github.com/explosion/spaCy/issues")
return n

103
spacy/tokens/token.pyx
View File

@ -1,5 +1,5 @@
# coding: utf8
# cython: infer_types=True
# coding: utf8
from __future__ import unicode_literals
from libc.string cimport memcpy
@ -8,20 +8,15 @@ from cpython.mem cimport PyMem_Malloc, PyMem_Free
from cython.view cimport array as cvarray
cimport numpy as np
np.import_array()
import numpy
import six
from ..typedefs cimport hash_t
from ..lexeme cimport Lexeme
from .. import parts_of_speech
from ..attrs cimport LEMMA
from ..attrs cimport ID, ORTH, NORM, LOWER, SHAPE, PREFIX, SUFFIX, LENGTH, CLUSTER
from ..attrs cimport POS, LEMMA, TAG, DEP
from ..parts_of_speech cimport CCONJ, PUNCT
from ..attrs cimport IS_ALPHA, IS_ASCII, IS_DIGIT, IS_LOWER, IS_PUNCT, IS_SPACE
from ..attrs cimport IS_BRACKET
from ..attrs cimport IS_QUOTE
@ -29,12 +24,13 @@ from ..attrs cimport IS_LEFT_PUNCT
from ..attrs cimport IS_RIGHT_PUNCT
from ..attrs cimport IS_TITLE, IS_UPPER, LIKE_URL, LIKE_NUM, LIKE_EMAIL, IS_STOP
from ..attrs cimport IS_OOV
from ..lexeme cimport Lexeme
from ..compat import is_config
cdef class Token:
"""An individual token --- i.e. a word, punctuation symbol, whitespace, etc.
"""
An individual token --- i.e. a word, punctuation symbol, whitespace, etc.
"""
def __cinit__(self, Vocab vocab, Doc doc, int offset):
self.vocab = vocab
@ -46,7 +42,9 @@ cdef class Token:
return hash((self.doc, self.i))
def __len__(self):
'''Number of unicode characters in token.text'''
"""
Number of unicode characters in token.text.
"""
return self.c.lex.length
def __unicode__(self):
@ -56,7 +54,7 @@ cdef class Token:
return self.text.encode('utf8')
def __str__(self):
if six.PY3:
if is_config(python3=True):
return self.__unicode__()
return self.__bytes__()
@ -83,27 +81,30 @@ cdef class Token:
raise ValueError(op)
cpdef bint check_flag(self, attr_id_t flag_id) except -1:
'''Check the value of a boolean flag.
"""
Check the value of a boolean flag.
Arguments:
flag_id (int): The ID of the flag attribute.
Returns:
is_set (bool): Whether the flag is set.
'''
"""
return Lexeme.c_check_flag(self.c.lex, flag_id)
def nbor(self, int i=1):
'''Get a neighboring token.
"""
Get a neighboring token.
Arguments:
i (int): The relative position of the token to get. Defaults to 1.
Returns:
neighbor (Token): The token at position self.doc[self.i+i]
'''
"""
return self.doc[self.i+i]
def similarity(self, other):
'''Compute a semantic similarity estimate. Defaults to cosine over vectors.
"""
Compute a semantic similarity estimate. Defaults to cosine over vectors.
Arguments:
other:
@ -111,7 +112,7 @@ cdef class Token:
Token and Lexeme objects.
Returns:
score (float): A scalar similarity score. Higher is more similar.
'''
"""
if 'similarity' in self.doc.user_token_hooks:
return self.doc.user_token_hooks['similarity'](self)
if self.vector_norm == 0 or other.vector_norm == 0:
@ -209,9 +210,9 @@ cdef class Token:
self.c.dep = label
property has_vector:
'''
"""
A boolean value indicating whether a word vector is associated with the object.
'''
"""
def __get__(self):
if 'has_vector' in self.doc.user_token_hooks:
return self.doc.user_token_hooks['has_vector'](self)
@ -223,11 +224,11 @@ cdef class Token:
return False
property vector:
'''
"""
A real-valued meaning representation.
Type: numpy.ndarray[ndim=1, dtype='float32']
'''
"""
def __get__(self):
if 'vector' in self.doc.user_token_hooks:
return self.doc.user_token_hooks['vector'](self)
@ -245,6 +246,7 @@ cdef class Token:
property repvec:
def __get__(self):
raise AttributeError("repvec was renamed to vector in v0.100")
property has_repvec:
def __get__(self):
raise AttributeError("has_repvec was renamed to has_vector in v0.100")
@ -265,7 +267,8 @@ cdef class Token:
property lefts:
def __get__(self):
"""The leftward immediate children of the word, in the syntactic
"""
The leftward immediate children of the word, in the syntactic
dependency parse.
"""
cdef int nr_iter = 0
@ -282,8 +285,10 @@ cdef class Token:
property rights:
def __get__(self):
"""The rightward immediate children of the word, in the syntactic
dependency parse."""
"""
The rightward immediate children of the word, in the syntactic
dependency parse.
"""
cdef const TokenC* ptr = self.c + (self.c.r_edge - self.i)
tokens = []
cdef int nr_iter = 0
@ -300,19 +305,21 @@ cdef class Token:
yield t
property children:
'''A sequence of the token's immediate syntactic children.
"""
A sequence of the token's immediate syntactic children.
Yields: Token A child token such that child.head==self
'''
"""
def __get__(self):
yield from self.lefts
yield from self.rights
property subtree:
'''A sequence of all the token's syntactic descendents.
"""
A sequence of all the token's syntactic descendents.
Yields: Token A descendent token such that self.is_ancestor(descendent)
'''
"""
def __get__(self):
for word in self.lefts:
yield from word.subtree
@ -321,26 +328,29 @@ cdef class Token:
yield from word.subtree
property left_edge:
'''The leftmost token of this token's syntactic descendents.
"""
The leftmost token of this token's syntactic descendents.
Returns: Token The first token such that self.is_ancestor(token)
'''
"""
def __get__(self):
return self.doc[self.c.l_edge]
property right_edge:
'''The rightmost token of this token's syntactic descendents.
"""
The rightmost token of this token's syntactic descendents.
Returns: Token The last token such that self.is_ancestor(token)
'''
"""
def __get__(self):
return self.doc[self.c.r_edge]
property ancestors:
'''A sequence of this token's syntactic ancestors.
"""
A sequence of this token's syntactic ancestors.
Yields: Token A sequence of ancestor tokens such that ancestor.is_ancestor(self)
'''
"""
def __get__(self):
cdef const TokenC* head_ptr = self.c
# guard against infinite loop, no token can have
@ -356,25 +366,29 @@ cdef class Token:
return self.is_ancestor(descendant)
def is_ancestor(self, descendant):
'''Check whether this token is a parent, grandparent, etc. of another
"""
Check whether this token is a parent, grandparent, etc. of another
in the dependency tree.
Arguments:
descendant (Token): Another token.
Returns:
is_ancestor (bool): Whether this token is the ancestor of the descendant.
'''
"""
if self.doc is not descendant.doc:
return False
return any( ancestor.i == self.i for ancestor in descendant.ancestors )
property head:
'''The syntactic parent, or "governor", of this token.
"""
The syntactic parent, or "governor", of this token.
Returns: Token
'''
"""
def __get__(self):
"""The token predicted by the parser to be the head of the current token."""
"""
The token predicted by the parser to be the head of the current token.
"""
return self.doc[self.i + self.c.head]
def __set__(self, Token new_head):
# this function sets the head of self to new_head
@ -467,10 +481,11 @@ cdef class Token:
self.c.head = rel_newhead_i
property conjuncts:
'''A sequence of coordinated tokens, including the token itself.
"""
A sequence of coordinated tokens, including the token itself.
Yields: Token A coordinated token
'''
"""
def __get__(self):
"""Get a list of conjoined words."""
cdef Token word
@ -501,7 +516,9 @@ cdef class Token:
return iob_strings[self.c.ent_iob]
property ent_id:
'''An (integer) entity ID. Usually assigned by patterns in the Matcher.'''
"""
An (integer) entity ID. Usually assigned by patterns in the Matcher.
"""
def __get__(self):
return self.c.ent_id
@ -509,7 +526,9 @@ cdef class Token:
self.c.ent_id = key
property ent_id_:
'''A (string) entity ID. Usually assigned by patterns in the Matcher.'''
"""
A (string) entity ID. Usually assigned by patterns in the Matcher.
"""
def __get__(self):
return self.vocab.strings[self.c.ent_id]